© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5351
    Prev
    Next
    INDEX
    Explanations

    words related to a specific religion and its practices

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms and symbols

    np_token-act-pair-logits · gpt-4o-mini

    Lord Narasimha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zędu
    -0.52
    sbericht
    -0.49
    ירות
    -0.49
    เภ
    -0.48
     Polk
    -0.47
    ViewFeatures
    -0.45
     Indien
    -0.45
     toiminta
    -0.44
     aluguel
    -0.44
    iprot
    -0.44
    POSITIVE LOGITS
    +#+#
    0.77
    rungsseite
    0.75
    HasForeignKey
    0.69
     للاسماء
    0.66
     gyhoeddwyd
    0.65
     للمعارف
    0.64
    énégal
    0.59
     beginnetje
    0.58
     ComVisible
    0.57
    argout
    0.52
    Activations Density 0.606%

    No Known Activations